See it in action
Why OpenFlowKit?
Every diagramming tool makes a compromise. OpenFlowKit doesn't.
| Tool | What's missing |
|---|
| Excalidraw / tldraw | Freeform whiteboards — no structured diagram types, no DSL, no code imports |
| Mermaid.js | Code-only — no visual canvas, no AI, no interactive editor |
| Draw.io | Decade-old UX — Limited AI integration, no developer import pipelines |
| Lucidchart / Miro | Cloud lock-in — expensive, account required, your data lives on their servers |
| PlantUML | Server-dependent rendering — no visual editor, no local-first model |
OpenFlowKit is the only MIT-licensed tool that combines a real workspace home, a professional visual canvas, bidirectional diagram-as-code, AI generation from 10 providers (including fully-local Ollama), automatic icon assignment from 1,600+ tech icons, anchored auto-layout, hardware-encoded cinematic MP4 export, and a Model Context Protocol server so Claude / Cursor / Windsurf can drive it directly — all with zero server-side storage.
Feature highlights
| OpenFlowKit | Excalidraw | Draw.io | Mermaid | Lucidchart |
|---|
| Visual canvas editor | ✅ | ✅ | ✅ | ❌ | ✅ |
| Bidirectional diagram-as-code | ✅ | ❌ | ❌ | ✅ | ❌ |
| AI generation (10 providers + Ollama) | ✅ | ❌ | ❌ | ❌ | Limited |
| Mermaid import (8 types) | ✅ | ❌ | ⚠️ | ✅ | ❌ |
| Auto-icon assignment (1,600+) | ✅ | ❌ | ❌ | ❌ | ❌ |
| AWS / Azure / GCP / CNCF icons | ✅ | ❌ | ✅ | Partial | ✅ |
| Anchored auto-layout (pin nodes) | ✅ | ❌ | ❌ | ❌ | ❌ |
| Cinematic MP4 export (WebCodecs) | ✅ | ❌ | ❌ | ❌ | ❌ |
| Figma export (editable SVG) | ✅ | ❌ | ❌ | ❌ | ❌ |
| No account required | ✅ | ✅ | ✅ | ✅ | ❌ |
| Open source (MIT) | ✅ | ✅ | ✅ | ✅ | ❌ |
Paste Mermaid → Beautiful Diagrams
Paste any Mermaid flowchart, architecture, state diagram, class diagram, ER diagram, sequence diagram, mindmap, or journey — all 8 diagram families. OpenFlowKit renders it on a visual canvas and automatically assigns the correct branded icon to every technology node.
flowchart TD
API[Express API] --> DB[(PostgreSQL)]
DB --> Cache[Redis Cache]
Cache --> Queue[RabbitMQ]
Paste this → you get the Express wordmark, PostgreSQL elephant, Redis logo, and RabbitMQ icon — all auto-detected, all beautifully laid out. No other tool does this.
1,600+ icons from developer, AWS, Azure, CNCF, and GCP catalogs are matched automatically based on node labels. No manual drag-and-drop. No configuration.
How it works
- Paste Mermaid on the canvas or in the code panel
- Semantic classifier detects technology names (PostgreSQL, Redis, Express, Lambda, etc.)
- Icon matcher searches 1,600+ icons across all catalogs — exact match, then alias, then substring
- Enricher assigns colors, icons, and provider SVGs to every node
- ELK layout arranges everything cleanly
Mermaid quality gates
npm run test:mermaid runs the broad Mermaid parser/plugin/round-trip gatenpm run test:mermaid:layout runs the layout, import-state, and recovery corpus gatenpm run test:mermaid:gold runs both together
AI generation (API key required)
Describe your system in plain English. AI generates a diagram on the canvas with correct icons applied automatically.
| Prompt | Output |
|---|
| "Node.js API with PostgreSQL and Redis" | 3 nodes with correct icons |
| "AWS Lambda → SQS → DynamoDB" | 3 nodes with AWS icons |
| "React frontend → Express → MongoDB → S3" | 4 nodes across developer + AWS catalogs |
10 providers supported: Google Gemini, OpenAI, Anthropic Claude, Groq, Mistral, NVIDIA NIM, Cerebras, OpenRouter, Ollama (fully local), or any custom OpenAI-compatible endpoint. Bad DSL from any provider is now auto-repaired — the model sees its own broken output and the parser error, then returns corrected DSL in a single follow-up turn.
Home first, editor second
OpenFlowKit now treats the product as two clear surfaces:
- Home for creating, opening, duplicating, importing, and organizing flows
- Editor for actual canvas work once a real document exists
That means the app does not create a fake default flow just to get you onto the canvas. If you delete everything, your workspace can stay empty until you intentionally create the next flow.
Flowpilot — AI generation with any model
Flowpilot sits directly in the editor. Describe a system, paste source code, upload a screenshot, or ask it to refine what's already on the canvas. Your API key is stored in your browser and sent directly to the provider — OpenFlowKit's servers never see it.
10 providers. Bring your own key. Switch any time. One runs entirely on your laptop.
| Provider | Default model | Why use it |
|---|
| 🦙 Ollama (local) | llama3.2 | Fully offline. No key, no network, no cost. |
| Google Gemini | gemini-2.5-flash-lite | Free tier available, fast, browser-safe |
| OpenAI | gpt-5-mini | Best reasoning for complex architectures |
| Anthropic Claude | claude-sonnet-4-6 | Excellent code and system understanding |
| Groq | meta-llama/llama-4-scout-17b-16e-instruct | Fastest open-source inference available |
| Mistral | mistral-large-latest | Strong European privacy-first alternative |
| NVIDIA NIM | meta/llama-4-maverick-17b-128e-instruct | Enterprise GPU inference |
| Cerebras | gpt-oss-120b | Ultra-fast on WSE-3 silicon |
| OpenRouter | google/gemini-2.5-pro | Access 300+ models through one key |
| Custom endpoint | Any model | LM Studio, vLLM, or any OpenAI-compatible API |
No proxy. No middleman. Direct browser-to-provider requests.
OpenFlow DSL — diagram as code
Every diagram has a live code panel. Edit the canvas → code updates. Edit the code → canvas updates. Two-way, always in sync.
flowchart TB
client[React App] --> gateway[API Gateway]
gateway --> auth[Auth Service]
gateway --> orders[Orders Service]
orders --> db[(PostgreSQL)]
orders --> cache[(Redis)]
auth --> db
- Mermaid-compatible syntax — paste any Mermaid and it renders with auto-assigned icons
- Specify icons directly:
{ archProvider: "developer", archResourceType: "database-postgresql" }
- Auto-icon resolution: nodes are enriched with the correct branded icon based on their label
- Export to Mermaid, PlantUML, or JSON
- Version snapshots — restore any previous state
Structured diagram families
Not a freeform whiteboard. Structured diagram types with opinionated defaults, correct relationship semantics, and purpose-built node styles.
- 🔷 Flowcharts — processes, decision trees, system flows
- ☁️ Architecture — AWS / Azure / GCP / CNCF cloud provider icons built in
- 🗄️ Entity-Relationship — typed fields, FK edges, one-to-many / many-to-many notation
- 📐 Class diagrams — UML with inheritance, composition, and interface relationships
- ↔️ Sequence diagrams — async messages, actors, and lifelines
- 🧠 Mind maps — collapsible radial trees with auto-layout
- 🛤️ User journeys — steps, phases, and sentiment scoring
- ⚙️ State machines — transitions, guards, entry and exit actions
Editor workflow built for technical diagrams
OpenFlowKit works best when you move between the right surfaces instead of forcing everything through one panel:
- Toolbar add menu for quick insert actions
- Command Center for templates, import, assets, search, layout, pages, layers, and design systems
- Studio for Flowpilot, Mermaid, OpenFlow DSL, infra parsing, and linting
- Properties panel for exact visual and metadata edits
Large diagrams also get better organization with multi-page documents, layers, sections, and local-first document recovery.
🎬 Cinematic Export — hardware-encoded MP4, no other OSS tool ships this
Turn any diagram into an animated video walkthrough — node by node, edge by edge — entirely in your browser. No upload, no server, no third-party tool.
Designed for architecture reviews, onboarding docs, and demos where a static image doesn't cut it.
No other open-source diagramming tool does this.
On modern browsers (Chrome / Edge / Safari 16.4+ / Firefox 130+) OpenFlowKit encodes via WebCodecs VideoEncoder + an in-browser MP4 muxer — H.264 baseline, hardware-accelerated, faster than real-time, deterministic frame timing. No more dropped frames under load. MediaRecorder remains a fallback for older browsers, so the feature is purely additive.
🪄 MCP Server — drive OpenFlowKit from Claude Desktop, Cursor, Windsurf
Point any MCP client at the @vrun-design/openflowkit-mcp package and your AI assistant gains local-first diagramming tools — no API key, no cloud round-trip. Your client already has an LLM, so OpenFlowKit MCP supplies deterministic local validation, codebase analysis, templates, icon lookup, and viewer links.
{
"mcpServers": {
"openflowkit": {
"command": "npx",
"args": ["-y", "@vrun-design/openflowkit-mcp"]
}
}
}
Then ask Claude: "Read the OpenFlowKit DSL cheatsheet, create a checkout flow with a promo-code branch and a Stripe webhook step, validate it, and create a viewer URL." The DSL comes back in seconds and stays editable in OpenFlowKit.
- 8 local-first tools — validate DSL, create viewer URLs, analyze codebases, find icon slugs, fetch starter templates, and inspect capabilities (no API key, runs on your machine)
- 5 resources — DSL cheatsheet, template catalog, template bodies, full icon catalog, and per-provider icon catalogs
- 3 prompts — flowchart creation, Mermaid conversion, and codebase architecture, all using the client model
- Pure Node, zero infra cost — runs on the user's machine, ships via npm
Full setup, tool table, and workflow details in mcp-server/README.md.
Export everywhere
Build your diagram once. Take it anywhere.
- 🎬 Cinematic WebM / MP4 — animated build walkthrough, browser-only, no upload required
- PNG / SVG — transparent background, pixel-perfect at any resolution
- PDF — print-ready, vector-crisp
- Mermaid — paste directly into GitHub READMEs, Notion, Confluence, Linear
- PlantUML — for enterprise toolchains and legacy integrations
- Figma — full editable SVG import with preserved layers
- JSON — complete round-trip import/export, no data loss
Local-first by default — your data, your machine
Local-first is the default. Your saved flows live in your browser's IndexedDB. Your AI keys stay on your device — every request goes directly from your browser to the provider you chose. Exports are explicit and run entirely client-side. No accounts, no telemetry, no server-side storage.
Real-time P2P collaboration over WebRTC exists in the codebase as an opt-in beta (set VITE_COLLABORATION_ENABLED=true). It is off by default while we redesign the signaling path for production reliability — the local-first experience does not depend on it.
Canvas built for keyboard-first developers
| Shortcut | Action |
|---|
⌘ K / Ctrl K | Command bar — search, import, layout, assets, and actions |
⌘ \ / Ctrl \ | Toggle the live code panel |
⌘ Z / Ctrl Z | Full undo with complete history |
⌘ D / Ctrl D | Duplicate selection |
⌘ G / Ctrl G | Group selected nodes |
P | Pin / unpin selected nodes (anchored layout) |
⌘ / / Ctrl / | Keyboard shortcuts reference |
Plus: smart alignment guides, snap-to-grid, multi-select, pages, layers, sections, architecture lint, light/dark/system theme, and full i18n in 7 languages.
What we are improving next
Recently shipped (latest milestone):
- ✅ WebCodecs H.264 MP4 export — faster-than-realtime, hardware-accelerated, deterministic
- ✅ MCP server —
@vrun-design/openflowkit-mcp for Claude Desktop, Cursor, Windsurf, any MCP client
- ✅ Anchored layout — pin nodes so auto-layout arranges around them
- ✅ Ollama provider — fully offline diagramming, no API key, no cost
- ✅ AI self-correction loop — bad DSL → AI sees its own output + parser error → returns corrected DSL
- ✅ ELK in a Web Worker — layout no longer blocks the UI thread
- ✅ Flowchart corpus 12 → 20 fixtures with explicit known-gap pinning
Current roadmap focus:
render_to_svg MCP tool — headless SVG render so AI clients can see the diagram, not just code- GIF export for cinematic animations — MP4 ships today; GIF export for zero-conversion embeds is next
- Mermaid family coverage — gantt, c4, timeline, gitGraph, sankey, quadrant (view + edit-as-code)
- Mac / Linux / Windows desktop app — Tauri shell wrapping the existing web app
- better layers and page workflows for larger technical diagrams
- smarter auto-layout defaults with less cleanup after import
- performance boosts for bigger canvases and heavier sessions
Get started in 30 seconds
git clone https://github.com/Vrun-design/openflowkit.git
cd openflowkit
npm install
npm run dev
Open http://localhost:5173. Done.
Zero environment variables required. AI provider keys are configured in the in-app settings panel at runtime — nothing goes in .env.
Self-host
OpenFlowKit is a pure static SPA. There is no backend. Deploy the dist/ folder anywhere that serves HTML.
Cloudflare Pages / Netlify / Vercel:
npm run build
# upload dist/ to your provider
Docker:
docker build -t openflowkit .
docker run --rm -p 3045:3045 openflowkit
Open http://localhost:3045. The container serves the production build with nginx, SPA route fallback, long-lived caching for hashed assets, and the same security headers used by the static hosting path.
No database. No secrets. No infrastructure. One folder, or one container.
Tech stack
| Layer | Technology |
|---|
| Framework | React 19 + TypeScript 5 |
| Build | Vite 6 |
| Canvas | React Flow (XYFlow) |
| Auto-layout | ELK.js — runs in a Web Worker, off the main thread |
| Video export | WebCodecs VideoEncoder + mp4-muxer (MediaRecorder fallback) |
| State | Zustand |
| Storage | IndexedDB — local-first, no backend |
| Styling | Tailwind CSS |
| Agent surface | @vrun-design/openflowkit-mcp — Model Context Protocol stdio |
| Collaboration | WebRTC P2P (opt-in, off by default) |
| i18n | react-i18next — 7 languages |
| Testing | Vitest + Playwright |
Contributing
All contributions are welcome — bug fixes, new diagram types, parser improvements, translations, and documentation.
Start here:
npm run dev # development server at localhost:5173
npm run test # unit tests via Vitest
npm run test:e2e # end-to-end tests via Playwright
npm run lint # ESLint + TypeScript type-check
Good first issues are tagged good first issue. Before opening a PR, please read CONTRIBUTING.md.
